Upload 7 files

README.md

@@ -1,18 +1,3 @@
----
-datasets:
-- FlameF0X/DialogMLM-50K
-language:
-- en
-tags:
-- text-generation-inference
-library_name: transformers
-pipeline_tag: text-generation
----
-
-> I know that you dont see any differences in the README.md, but I've trained the model to val loss 1.6836 than the previous version.
-> I aslo try to fix all the previous errors when you tired to laod the model.
-> Please tell me if you find any bugs or anything useful!
-
 # Snowflake-G0-Release
 
 This is the initial release of the Snowflake series language models, trained on the DialogMLM-50K dataset with optimized memory usage.
@@ -45,4 +30,4 @@ model = AutoModel.from_pretrained("path/to/snowflake_g0_release")
 - Weight tying between embedding and output layers
 - Half-precision model storage
 
-The model weights are stored in both PyTorch (.bin) and safetensors format for improved security, loading efficiency, and compatibility.
+The model weights are stored in both PyTorch (.bin) and safetensors format for improved security, loading efficiency, and compatibility.

config.json

@@ -2,7 +2,6 @@
   "architectures": [
     "SnowflakeCore"
   ],
-  "model_type": "gpt2",
   "hidden_size": 384,
   "intermediate_size": 768,
   "max_position_embeddings": 384,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71cc42d8dfe014ef49409730a63eb30e085822c768360f8263b9c0428372086d
-size 33274540
+oid sha256:3566ff5e952ec4dfab158f1534ba1b16ae9e765d7e8b3e69bc05b6ad8d5a7abf
+size 33274556

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb569d5315b86cd6109c43c565f3400e3127765ffa7fe7c8ca9f53b757377a1
+oid sha256:90a8941a9e5e6156cc133140a869315ddec182a11532c26f1f281ff42f3b2496
 size 66559270